
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.express as px
from plotly.subplots import make_subplots
from datetime import datetime


covid_df =pd.read_csv("C:/Users/Vinod/Downloads/Covid India Data Analysis Project_files/covid india data sets/covid_19_india.csv")


covid_df.head(10)


covid_df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 15086 entries, 0 to 15085
Data columns (total 9 columns):
 #   Column                    Non-Null Count  Dtype  
---  ------                    --------------  -----  
 0   Sno                       15086 non-null  int64  
 1   Date                      15086 non-null  object 
 2   Time                      15086 non-null  object 
 3   State/UnionTerritory      15086 non-null  object 
 4   ConfirmedIndianNational   446 non-null    float64
 5   ConfirmedForeignNational  446 non-null    float64
 6   Cured                     15086 non-null  int64  
 7   Deaths                    15086 non-null  int64  
 8   Confirmed                 15086 non-null  int64  
dtypes: float64(2), int64(4), object(3)
memory usage: 1.0+ MB


covid_df.describe()


vaccine_df = pd.read_csv("C:/Users/Vinod/Downloads/Covid India Data Analysis Project_files/covid india data sets/covid_vaccine_statewise.csv")


vaccine_df.head(7)


covid_df.drop(["Sno", "Time", "ConfirmedIndianNational", "ConfirmedForeignNational"], inplace = True, axis = 1)


covid_df.head()


covid_df['Date'] = pd.to_datetime(covid_df['Date'], format = '%m/%d/%Y')


covid_df.head()


# Active Cases

covid_df['Active_Cases'] = covid_df['Confirmed'] - (covid_df['Cured'] + covid_df['Deaths'])
covid_df.tail()


statewise = pd.pivot_table(covid_df, values = ["Confirmed","Deaths","Cured"],
                          index = "State/UnionTerritory", aggfunc = max)


statewise["Recovery Rate"] = statewise["Cured"]*100/statewise["Confirmed"]


statewise["Mortality Rate"] = statewise["Deaths"]*100/statewise["Confirmed"]


statewise = statewise.sort_values(by = "Confirmed", ascending = False)


statewise.style.background_gradient(cmap = "cubehelix")


# Top 10 Active Cases

top_10_Active_Cases = covid_df.groupby(by = "State/UnionTerritory").max()[['Active_Cases', 'Date']].sort_values(by = ['Active_Cases'], ascending = False).reset_index()

fig = plt.figure(figsize = (16,9))

plt.title("Top 10 states with most active cases in India", size = 25)

ax = sns.barplot(data = top_10_Active_Cases.iloc[:10], y = "Active_Cases", x = "State/UnionTerritory", linewidth =2, edgecolor = "red")

plt.xlabel('States')
plt.ylabel('Total Active Cases')
plt.show()


# Top 10 States with highest deaths

top_10_deaths = covid_df.groupby(by = "State/UnionTerritory").max()[['Deaths', 'Date']].sort_values(by = ['Deaths'], ascending = False).reset_index()

fig = plt.figure(figsize = (18,5))

plt.title("Top 10 states with most deaths in India", size = 25)

ax = sns.barplot(data = top_10_deaths.iloc[:10], y = "Deaths", x = "State/UnionTerritory", linewidth =2, edgecolor = "black")

plt.xlabel('States')
plt.ylabel('Total Death Cases')
plt.show()


# Growth Trend

fig = plt.figure(figsize = (12,6))

ax = sns.lineplot(data = covid_df[covid_df['State/UnionTerritory'].isin(['Maharashtra','Karnataka','Kerala','Tamil Nadu','Uttar Pradesh'])],x = 'Date', y = 'Active_Cases', hue = 'State/UnionTerritory')

ax.set_title("Top 5 Affected states in India", size = 16)

Text(0.5, 1.0, 'Top 5 Affected states in India')


vaccine_df.head(10)


vaccine_df.rename(columns = {'Updated On' : 'Vaccine_Date'}, inplace = True)


vaccine_df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 7845 entries, 0 to 7844
Data columns (total 24 columns):
 #   Column                               Non-Null Count  Dtype  
---  ------                               --------------  -----  
 0   Vaccine_Date                         7845 non-null   object 
 1   State                                7845 non-null   object 
 2   Total Doses Administered             7621 non-null   float64
 3   Sessions                             7621 non-null   float64
 4    Sites                               7621 non-null   float64
 5   First Dose Administered              7621 non-null   float64
 6   Second Dose Administered             7621 non-null   float64
 7   Male (Doses Administered)            7461 non-null   float64
 8   Female (Doses Administered)          7461 non-null   float64
 9   Transgender (Doses Administered)     7461 non-null   float64
 10   Covaxin (Doses Administered)        7621 non-null   float64
 11  CoviShield (Doses Administered)      7621 non-null   float64
 12  Sputnik V (Doses Administered)       2995 non-null   float64
 13  AEFI                                 5438 non-null   float64
 14  18-44 Years (Doses Administered)     1702 non-null   float64
 15  45-60 Years (Doses Administered)     1702 non-null   float64
 16  60+ Years (Doses Administered)       1702 non-null   float64
 17  18-44 Years(Individuals Vaccinated)  3733 non-null   float64
 18  45-60 Years(Individuals Vaccinated)  3734 non-null   float64
 19  60+ Years(Individuals Vaccinated)    3734 non-null   float64
 20  Male(Individuals Vaccinated)         160 non-null    float64
 21  Female(Individuals Vaccinated)       160 non-null    float64
 22  Transgender(Individuals Vaccinated)  160 non-null    float64
 23  Total Individuals Vaccinated         5919 non-null   float64
dtypes: float64(22), object(2)
memory usage: 1.4+ MB


vaccine_df.isnull().sum()

Vaccine_Date                              0
State                                     0
Total Doses Administered                224
Sessions                                224
 Sites                                  224
First Dose Administered                 224
Second Dose Administered                224
Male (Doses Administered)               384
Female (Doses Administered)             384
Transgender (Doses Administered)        384
 Covaxin (Doses Administered)           224
CoviShield (Doses Administered)         224
Sputnik V (Doses Administered)         4850
AEFI                                   2407
18-44 Years (Doses Administered)       6143
45-60 Years (Doses Administered)       6143
60+ Years (Doses Administered)         6143
18-44 Years(Individuals Vaccinated)    4112
45-60 Years(Individuals Vaccinated)    4111
60+ Years(Individuals Vaccinated)      4111
Male(Individuals Vaccinated)           7685
Female(Individuals Vaccinated)         7685
Transgender(Individuals Vaccinated)    7685
Total Individuals Vaccinated           1926
dtype: int64


vaccination = vaccine_df.drop(columns = ['Sputnik V (Doses Administered)', 'AEFI', '18-44 Years (Doses Administered)','45-60 Years (Doses Administered)','60+ Years (Doses Administered)'], axis = 1)


vaccination.head()


# Male vs Female vaccination

male = vaccination['Male(Individuals Vaccinated)'].sum()
female = vaccination['Female(Individuals Vaccinated)'].sum()
px.pie(names = ['Male', 'Female'], values = [male, female], title = 'Male and Female Vaccination')


# Removing the rows

vaccine = vaccine_df[vaccine_df.State != 'India']
vaccine


vaccine.rename(columns = {'Total Individuals Vaccinated' : 'Total'}, inplace = True)
vaccine.head()

C:\Users\Vinod\AppData\Local\Temp\ipykernel_8940\1867626165.py:1: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy


# Most vaccinated State

max_vac = vaccine.groupby('State')['Total'].sum().to_frame('Total')
max_vac = max_vac.sort_values('Total', ascending = False)[:5]
max_vac


# Top 5 Vaccinated States in India

fig = plt.figure(figsize = (10,5))

plt.title("Top 5 Vaccinated States in India", size = 20)

x = sns.barplot(data = max_vac.iloc[:10], y = max_vac.Total, x = max_vac.index, linewidth =2, edgecolor = "black")

plt.xlabel('States')
plt.ylabel('Vaccination')
plt.show()


min_vac = vaccine.groupby('State')['Total'].sum().to_frame('Total')
min_vac = min_vac.sort_values('Total', ascending = True)[:5]
min_vac


# Least 5 Vaccinated States in India

fig = plt.figure(figsize = (15,5))

plt.title("Least 5 Vaccinated States in India", size = 20)

x = sns.barplot(data = min_vac.iloc[:10], y = min_vac.Total, x = min_vac.index, linewidth =2, edgecolor = "black")

plt.xlabel('States')
plt.ylabel('Vaccination')
plt.show()

	Sno	Date	Time	State/UnionTerritory	ConfirmedIndianNational	Confirmed
0	1	5/19/2021	6:00:00 PM	Kerala	1.0	1
1	2	5/19/2021	6:00:00 PM	Kerala	1.0	1
2	3	5/19/2021	6:00:00 PM	Kerala	2.0	2
3	4	5/19/2021	6:00:00 PM	Kerala	3.0	3
4	5	5/19/2021	6:00:00 PM	Kerala	3.0	3
5	6	5/19/2021	6:00:00 PM	Kerala	3.0	3
6	7	5/19/2021	6:00:00 PM	Kerala	3.0	3
7	8	5/19/2021	6:00:00 PM	Kerala	3.0	3
8	9	5/19/2021	6:00:00 PM	Kerala	3.0	3
9	10	5/19/2021	6:00:00 PM	Kerala	3.0	3

	Sno	ConfirmedIndianNational	ConfirmedForeignNational	Cured	Deaths	Confirmed
count	15086.000000	446.000000	446.000000	1.508600e+04	15086.000000	1.508600e+04
mean	7543.500000	12.188341	1.495516	1.747937e+05	2721.084449	1.942820e+05
std	4355.097416	21.582253	3.576292	3.648330e+05	7182.672358	4.095184e+05
min	1.000000	0.000000	0.000000	0.000000e+00	0.000000	0.000000e+00
25%	3772.250000	1.000000	0.000000	1.685000e+03	12.000000	2.935500e+03
50%	7543.500000	3.000000	0.000000	1.964700e+04	364.000000	2.608150e+04
75%	11314.750000	13.000000	1.000000	2.087552e+05	2170.000000	2.216012e+05
max	15086.000000	177.000000	14.000000	4.927480e+06	83777.000000	5.433506e+06

	Updated On	State	Total Doses Administered	Sessions	Sites	First Dose Administered	Male (Doses Administered)	Female (Doses Administered)	Transgender (Doses Administered)	...	18-44 Years (Doses Administered)	45-60 Years (Doses Administered)	60+ Years (Doses Administered)	18-44 Years(Individuals Vaccinated)	45-60 Years(Individuals Vaccinated)	60+ Years(Individuals Vaccinated)	Male(Individuals Vaccinated)	Female(Individuals Vaccinated)	Transgender(Individuals Vaccinated)	Total Individuals Vaccinated
0	16/01/2021	India	48276.0	3455.0	2957.0	48276.0	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	23757.0	24517.0	2.0	48276.0
1	17/01/2021	India	58604.0	8532.0	4954.0	58604.0	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	27348.0	31252.0	4.0	58604.0
2	18/01/2021	India	99449.0	13611.0	6583.0	99449.0	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	41361.0	58083.0	5.0	99449.0
3	19/01/2021	India	195525.0	17855.0	7951.0	195525.0	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	81901.0	113613.0	11.0	195525.0
4	20/01/2021	India	251280.0	25472.0	10504.0	251280.0	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	98111.0	153145.0	24.0	251280.0
5	21/01/2021	India	365965.0	32226.0	12600.0	365965.0	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	132784.0	233143.0	38.0	365965.0
6	22/01/2021	India	549381.0	36988.0	14115.0	549381.0	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	193899.0	355402.0	80.0	549381.0

	Date	State/UnionTerritory	Cured	Deaths	Confirmed	Active_Cases
15081	2020-02-03	Telangana	485644	3012	536766	48110
15082	2020-02-02	Tripura	36402	450	42776	5924
15083	2020-02-01	Uttarakhand	214426	5132	295790	76232
15084	2020-01-31	Uttar Pradesh	1483249	18072	1637663	136342
15085	2020-01-30	West Bengal	1026492	13576	1171861	131793

	Confirmed	Cured	Deaths	Recovery Rate	Mortality Rate
State/UnionTerritory
Maharashtra	5433506	4927480	83777	90.686934	1.541859
Karnataka	2272374	1674487	22838	73.688882	1.005028
Kerala	2200706	1846105	6612	83.886944	0.300449
Tamil Nadu	1664350	1403052	18369	84.300297	1.103674
Uttar Pradesh	1637663	1483249	18072	90.571076	1.103524
Andhra Pradesh	1475372	1254291	9580	85.015237	0.649328
Delhi	1402873	1329899	22111	94.798246	1.576123
West Bengal	1171861	1026492	13576	87.595030	1.158499
Chhattisgarh	925531	823113	12036	88.934136	1.300443
Rajasthan	879664	713129	7080	81.068340	0.804853
Gujarat	766201	660489	9269	86.203098	1.209735
Madhya Pradesh	742718	652612	7139	87.868074	0.961199
Haryana	709689	626852	6923	88.327704	0.975498
Bihar	664115	595377	4039	89.649684	0.608178
Odisha	633302	536595	2357	84.729718	0.372176
Telangana	536766	485644	3012	90.475924	0.561138
Punjab	511652	427058	12317	83.466497	2.407300
Telengana	443360	362160	2312	81.685312	0.521472
Assam	340858	290774	2344	85.306491	0.687676
Jharkhand	320934	284805	4601	88.742545	1.433628
Uttarakhand	295790	214426	5132	72.492647	1.735015
Jammu and Kashmir	251919	197701	3293	78.478003	1.307166
Himachal Pradesh	166678	129330	2460	77.592724	1.475900
Goa	138776	112633	2197	81.161728	1.583127
Puducherry	87749	69060	1212	78.701752	1.381212
Chandigarh	56513	48831	647	86.406667	1.144869
Tripura	42776	36402	450	85.099121	1.051992
Manipur	40683	33466	612	82.260404	1.504314
Meghalaya	24872	19185	355	77.134931	1.427308
Arunachal Pradesh	22462	19977	88	88.936871	0.391773
Nagaland	18714	14079	228	75.232446	1.218339
Ladakh	16784	15031	170	89.555529	1.012869
Sikkim	11689	8427	212	72.093421	1.813671
Dadra and Nagar Haveli and Daman and Diu	9652	8944	4	92.664733	0.041442
Cases being reassigned to states	9265	0	0	0.000000	0.000000
Mizoram	9252	7094	29	76.675313	0.313446
Andaman and Nicobar Islands	6674	6359	92	95.280192	1.378484
Lakshadweep	5212	3915	15	75.115119	0.287797
Unassigned	77	0	0	0.000000	0.000000
Daman & Diu	2	0	0	0.000000	0.000000

	Date	State/UnionTerritory	Confirmed
0	2021-05-19	Kerala	1
1	2021-05-19	Kerala	1
2	2021-05-19	Kerala	2
3	2021-05-19	Kerala	3
4	2021-05-19	Kerala	3

	Vaccine_Date	State	Total Doses Administered	Sessions	Sites	First Dose Administered	Second Dose Administered	Male (Doses Administered)	Female (Doses Administered)	Transgender (Doses Administered)	...	18-44 Years (Doses Administered)	45-60 Years (Doses Administered)	60+ Years (Doses Administered)	18-44 Years(Individuals Vaccinated)	45-60 Years(Individuals Vaccinated)	60+ Years(Individuals Vaccinated)	Male(Individuals Vaccinated)	Female(Individuals Vaccinated)	Transgender(Individuals Vaccinated)	Total Individuals Vaccinated
212	16/01/2021	Andaman and Nicobar Islands	23.0	2.0	2.0	23.0	0.0	12.0	11.0	0.0	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	23.0
213	17/01/2021	Andaman and Nicobar Islands	23.0	2.0	2.0	23.0	0.0	12.0	11.0	0.0	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	23.0
214	18/01/2021	Andaman and Nicobar Islands	42.0	9.0	2.0	42.0	0.0	29.0	13.0	0.0	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	42.0
215	19/01/2021	Andaman and Nicobar Islands	89.0	12.0	2.0	89.0	0.0	53.0	36.0	0.0	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	89.0
216	20/01/2021	Andaman and Nicobar Islands	124.0	16.0	3.0	124.0	0.0	67.0	57.0	0.0	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	124.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
7840	11/08/2021	West Bengal	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
7841	12/08/2021	West Bengal	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
7842	13/08/2021	West Bengal	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
7843	14/08/2021	West Bengal	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
7844	15/08/2021	West Bengal	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN

	Total
State
Maharashtra	1.403075e+09
Uttar Pradesh	1.200575e+09
Rajasthan	1.141163e+09
Gujarat	1.078261e+09
West Bengal	9.250227e+08

	Total
State
Lakshadweep	2124715.0
Andaman and Nicobar Islands	8102125.0
Ladakh	9466289.0
Dadra and Nagar Haveli and Daman and Diu	11358600.0
Sikkim	16136752.0